Machine-learned potentials (MLPs) have exhibited remarkable accuracy, yet the lack of general-purpose MLPs for a broad spectrum of elements and their alloys limits their applicability. Here, we present a promising approach for constructing a unified general-purpose MLP for numerous elements, demonstrated through a model (UNEP-v1) for 16 elemental metals and their alloys. To achieve a complete representation of the chemical space, we show, via principal component analysis and diverse test datasets, that employing one-component and two-component systems suffices. Our unified UNEP-v1 model exhibits superior performance across various physical properties compared to a widely used embedded-atom method potential, while maintaining remarkable efficiency. We demonstrate our approach’s effectiveness through reproducing experimentally observed chemical order and stable phases, and large-scale simulations of plasticity and primary radiation damage in MoTaVW alloys.

The transformative impact of artificial intelligence (AI) technologies on materials science has revolutionized the study of materials problems. By leveraging well-characterized datasets derived from the scientific literature, AI-powered tools such as Natural Language Processing (NLP) have opened new avenues to accelerate materials research. The advances in NLP techniques and the development of large language models (LLMs) facilitate the efficient extraction and utilization of information. This review explores the application of NLP tools in materials science, focusing on automatic data extraction, materials discovery, and autonomous research. We also discuss the challenges and opportunities associated with utilizing LLMs and outline the prospects and advancements that will propel the field forward.

2D MXene materials have the advantages of versatile chemical composition, tunable layer thickness, and facile functionalization nature, and can be used as catalysts for the hydrogen evolution reaction (HER). However, tuning the thermal stability and activation of in-plane activity remain a challenge. We apply high-throughput density functional theory (DFT) calculations, together with a machine learning framework, to identify 2D MXene ordered binary alloy (OBA) activity trends and guide HER catalyst design. 2D MXenes of M_n+1X_nO₂ (n = 1, 2, 3; X = C, N) and OBA HER catalysts of M₂M′X₂O₂ and M₂M′₂X₃O₂ with 3d, 4d and 5d transition metal electrons were enumerated by screening, followed by catalytic activity, thermal stability, and conductivity computations. Our results indicate that 110 kinds of experimentally unexplored 2D MXene OBAs with thermostability and outstanding HER activity surpassing that of noble metal platinum were selected. Especially, the titanium element is mainly contained in the ideal catalysts of 2D MXene OBAs, which is consistent with the MXenes synthesized by experiments. Further, we show that descriptors developed using the AdaBoost ensemble learning model could accurately predict and uncover the essential geometric and chemical origin of HER activity, which is very consistent with the electronic insights. The advanced research strategy, which combines high-throughput computing with machine learning, shows robust ability for evaluating the activity trends and designing new complicated catalysts.

Designing a material with multiple desired properties is a great challenge, especially in a complex material system. Here, we propose a material design strategy to simultaneously optimize multiple targeted properties of multi-component Co-base superalloys via machine learning. The microstructural stability, γ′ solvus temperature, γ′ volume fraction, density, processing window, freezing range, and oxidation resistance were simultaneously optimized. A series of novel Co-base superalloys were successfully selected and experimentally synthesized from >210,000 candidates. The best performer, Co-36Ni-12Al-2Ti-4Ta-1W-2Cr, possesses the highest γ′ solvus temperature of 1266.5 °C without the precipitation of any deleterious phases, a γ′ volume fraction of 74.5% after aging for 1000 h at 1000 °C, a density of 8.68 g cm⁻³ and good high-temperature oxidation resistance at 1000 °C due to the formation of a protective alumina layer. Our approach paves a new way to rapidly design multi-component materials with desired multi-performance functionality.

Recent progress in material data mining has been driven by high-capacity models trained on large datasets. However, collecting experimental data (real data) has been extremely costly owing to the amount of human effort and expertise required. Here, we develop a novel transfer learning strategy to address problems of small or insufficient data. This strategy realizes the fusion of real and simulated data and the augmentation of training data in a data mining procedure. For a specific task of grain instance image segmentation, this strategy aims to generate synthetic data by fusing the images obtained from simulating the physical mechanism of grain formation and the “image style” information in real images. The results show that the model trained with the acquired synthetic data and only 35% of the real data can already achieve competitive segmentation performance of a model trained on all of the real data. Because the time required to perform grain simulation and to generate synthetic data are almost negligible as compared to the effort for obtaining real data, our proposed strategy is able to exploit the strong prediction power of deep learning without significantly increasing the experimental burden of training data preparation.

Data provides a foundation for machine learning, which has accelerated data-driven materials design. The scientific literature contains a large amount of high-quality, reliable data, and automatically extracting data from the literature continues to be a challenge. We propose a natural language processing pipeline to capture both chemical composition and property data that allows analysis and prediction of superalloys. Within 3 h, 2531 records with both composition and property are extracted from 14,425 articles, coveringγ′ solvus temperature, density, solidus, and liquidus temperatures. A data-driven model forγ′ solvus temperature is built to predict unexplored Co-based superalloys with highγ′ solvus temperatures within a relative error of 0.81%. We test the predictions via synthesis and characterization of three alloys. A web-based toolkit as an online open-source platform is provided and expected to serve as the basis for a general method to search for targeted materials using data extracted from the literature.